Understand Me, if You Refer to Aspect Knowledge: Knowledge-Aware Gated Recurrent Memory Network

Xing, B; Tsang, IW

Understand Me, if You Refer to Aspect Knowledge: Knowledge-Aware Gated Recurrent Memory Network

Xing, B Tsang, IW

Permalink

Publisher:: IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
Publication Type:: Journal Article
Citation:: IEEE Transactions on Emerging Topics in Computational Intelligence, 2022, 6, (5), pp. 1092-1102
Issue Date:: 2022-10-01

Open Access

Copyright Clearance Process

Recently Added
In Progress
Open Access

This item is open access.

The embargo period expires on 15 Mar 2024

Adobe PDF

Download Accepted versionAdobe PDF (790.79 kB)

View on publisher's site

View statistics

Full metadata record

Field	Value	Language
dc.contributor.author	Xing, B
dc.contributor.author	Tsang, IW
dc.date.accessioned	2023-03-17T05:02:23Z
dc.date.available	2023-03-17T05:02:23Z
dc.date.issued	2022-10-01
dc.identifier.citation	IEEE Transactions on Emerging Topics in Computational Intelligence, 2022, 6, (5), pp. 1092-1102
dc.identifier.issn	2471-285X
dc.identifier.issn	2471-285X
dc.identifier.uri	http://hdl.handle.net/10453/167480
dc.description.abstract	Aspect-level sentiment classification (ASC) aims to predict the fine-grained sentiment polarity towards a given aspect mentioned in a review. Despite recent advances in ASC, enabling machines to preciously infer aspect sentiments is still challenging. This paper tackles two challenges in ASC: (1) due to lack of aspect knowledge, aspect representation derived in prior works is inadequate to represent aspect's exact meaning and property information; (2) prior works only capture either local syntactic information or global relational information, thus missing either one of them leads to insufficient syntactic information. To tackle these challenges, we propose a novel ASC model which not only end-to-end embeds and leverages aspect knowledge but also marries the two kinds of syntactic information and lets them compensate for each other. Our model includes four key components: (1) a knowledge-aware gated recurrent memory network recurrently integrates dynamically summarized aspect knowledge; (2) a dual syntax graph network combines both kinds of syntactic information to comprehensively capture sufficient syntactic information; (3) a knowledge integrating gate re-enhances the final representation with further needed aspect knowledge; (4) an aspect-to-context attention mechanism aggregates the aspect-related semantics from all hidden states into the final representation. Experimental results on several benchmark datasets demonstrate the effectiveness of our model, which overpass previous state-of-the-art models by large margins in terms of both Accuracy and Macro-F1. To facilitate further research in the community, we have released our source code at https://github.com/XingBowen714/KaGRMN-DSG-ABSA.
dc.language	English
dc.publisher	IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
dc.relation	http://purl.org/au-research/grants/arc/DP180100106
dc.relation	http://purl.org/au-research/grants/arc/DP200101328
dc.relation.ispartof	IEEE Transactions on Emerging Topics in Computational Intelligence
dc.relation.isbasedon	10.1109/TETCI.2022.3156989
dc.rights	info:eu-repo/semantics/embargoedAccess
dc.title	Understand Me, if You Refer to Aspect Knowledge: Knowledge-Aware Gated Recurrent Memory Network
dc.type	Journal Article
utslib.citation.volume	6
pubs.organisational-group	/University of Technology Sydney
pubs.organisational-group	/University of Technology Sydney/Faculty of Engineering and Information Technology
pubs.organisational-group	/University of Technology Sydney/Strength - AAII - Australian Artificial Intelligence Institute
utslib.copyright.status	open_access	*
utslib.copyright.embargo	2024-03-15T00:00:00+1000Z
dc.date.updated	2023-03-17T05:02:22Z
pubs.issue	5
pubs.publication-status	Published
pubs.volume	6
utslib.citation.issue	5

Abstract:

Aspect-level sentiment classification (ASC) aims to predict the fine-grained sentiment polarity towards a given aspect mentioned in a review. Despite recent advances in ASC, enabling machines to preciously infer aspect sentiments is still challenging. This paper tackles two challenges in ASC: (1) due to lack of aspect knowledge, aspect representation derived in prior works is inadequate to represent aspect's exact meaning and property information; (2) prior works only capture either local syntactic information or global relational information, thus missing either one of them leads to insufficient syntactic information. To tackle these challenges, we propose a novel ASC model which not only end-to-end embeds and leverages aspect knowledge but also marries the two kinds of syntactic information and lets them compensate for each other. Our model includes four key components: (1) a knowledge-aware gated recurrent memory network recurrently integrates dynamically summarized aspect knowledge; (2) a dual syntax graph network combines both kinds of syntactic information to comprehensively capture sufficient syntactic information; (3) a knowledge integrating gate re-enhances the final representation with further needed aspect knowledge; (4) an aspect-to-context attention mechanism aggregates the aspect-related semantics from all hidden states into the final representation. Experimental results on several benchmark datasets demonstrate the effectiveness of our model, which overpass previous state-of-the-art models by large margins in terms of both Accuracy and Macro-F1. To facilitate further research in the community, we have released our source code at https://github.com/XingBowen714/KaGRMN-DSG-ABSA.

Please use this identifier to cite or link to this item:

http://hdl.handle.net/10453/167480